Index: MicroBenchmarks/CMakeLists.txt
===================================================================
--- MicroBenchmarks/CMakeLists.txt
+++ MicroBenchmarks/CMakeLists.txt
@@ -6,3 +6,4 @@
 add_subdirectory(harris)
 add_subdirectory(ImageProcessing)
 add_subdirectory(LoopInterchange)
+add_subdirectory(MemFunctions)
Index: MicroBenchmarks/MemFunctions/CMakeLists.txt
===================================================================
--- /dev/null
+++ MicroBenchmarks/MemFunctions/CMakeLists.txt
@@ -0,0 +1,5 @@
+llvm_test_run(WORKDIR ${CMAKE_CURRENT_BINARY_DIR})
+
+llvm_test_executable(MemFunctions main.cpp)
+
+target_link_libraries(MemFunctions benchmark)
Index: MicroBenchmarks/MemFunctions/main.cpp
===================================================================
--- /dev/null
+++ MicroBenchmarks/MemFunctions/main.cpp
@@ -0,0 +1,118 @@
+//===- main.cc - Memory Functions Benchmarks ------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// Memory functions (memcmp, memcpy, ...) are typically recognized by the
+// compiler and expanded to specific asm patterns when the size is known at
+// compile time. THese microbenchmarks help catch potential CodeGen regressions.
+//
+// Note that these microbenchmarks do not represent a typical real-life
+// situation. They are designed to test the LLVM CodeGen. In particular,
+// real-life applications will typically be memory- rather than compute-bound
+// when manipulating memory.
+//
+//===----------------------------------------------------------------------===//
+
+#include "benchmark/benchmark.h"
+
+#include <cstring>
+#include <vector>
+
+// Benchmarks memcmp(p, q, size) where n is known at compile time.
+// The compiler typically inlines this to loads and compares.
+template <int kSize, typename Pred, typename Mod>
+void BM_MemCmp(benchmark::State &state) {
+  constexpr const size_t kNumElements = 4096 / kSize;
+
+  std::vector<char> p_storage(kNumElements * kSize);
+  std::vector<char> q_storage(kNumElements * kSize);
+  char* p = p_storage.data();
+  const char* q = q_storage.data();
+
+  for (int i = 0; i < kNumElements; ++i)
+    Mod().template Change<kSize>(p + i * kSize);
+
+  benchmark::DoNotOptimize(p_storage);
+  benchmark::DoNotOptimize(q_storage);
+
+  for (auto _ : state) {
+    for (int i = 0; i < kNumElements; ++i) {
+      int res = Pred()(memcmp(p + i * kSize, q + i * kSize, kSize));
+      benchmark::DoNotOptimize(res);
+    }
+  }
+  state.SetBytesProcessed(p_storage.size() * state.iterations());
+
+}
+
+
+// Predicates.
+struct EqZero {
+  bool operator()(int v) const { return v == 0; }
+};
+struct LessThanZero {
+  bool operator()(int v) const { return v < 0; }
+};
+struct GreaterThanZero {
+  bool operator()(int v) const { return v > 0; }
+};
+
+// Functors to change the first/mid/last or no value.
+struct None {
+  template <int kSize>
+  void Change(char* const p) const {}
+};
+struct First {
+  template <int kSize>
+  void Change(char* const p) const { p[0] = 128; }
+};
+struct Mid {
+  template <int kSize>
+  void Change(char* const p) const { p[kSize / 2] = 128; }
+};
+struct Last {
+  template <int kSize>
+  void Change(char* const p) const { p[kSize - 1] = 128; }
+};
+
+#define MEMCMP_BENCHMARK(size) \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, EqZero, None)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, EqZero, First)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, EqZero, Mid)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, EqZero, Last)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, LessThanZero, None)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, LessThanZero, First)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, LessThanZero, Mid)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, LessThanZero, Last)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, GreaterThanZero, None)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, GreaterThanZero, First)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, GreaterThanZero, Mid)->Unit(benchmark::kNanosecond); \
+  BENCHMARK_TEMPLATE(BM_MemCmp, size, GreaterThanZero, Last)->Unit(benchmark::kNanosecond);
+
+MEMCMP_BENCHMARK(1)
+MEMCMP_BENCHMARK(2)
+MEMCMP_BENCHMARK(3)
+MEMCMP_BENCHMARK(4)
+MEMCMP_BENCHMARK(5)
+MEMCMP_BENCHMARK(6)
+MEMCMP_BENCHMARK(7)
+MEMCMP_BENCHMARK(8)
+MEMCMP_BENCHMARK(15)
+MEMCMP_BENCHMARK(16)
+MEMCMP_BENCHMARK(31)
+MEMCMP_BENCHMARK(32)
+MEMCMP_BENCHMARK(63)
+MEMCMP_BENCHMARK(64)
+
+int main(int argc, char *argv[]) {
+  ::benchmark::Initialize(&argc, argv);
+  if (::benchmark::ReportUnrecognizedArguments(argc, argv))
+    return 1;
+  ::benchmark::RunSpecifiedBenchmarks();
+
+  return 0;
+}